Accepted author manuscript, 4.03 MB, PDF document
Final published version
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Cosmic ray muon clustering for the MicroBooNE liquid argon time projection chamber using sMask-RCNN
AU - The MicroBooNE collaboration
AU - Abratenko, P.
AU - An, R.
AU - Anthony, J.
AU - Arellano, L.
AU - Asaadi, J.
AU - Ashkenazi, A.
AU - Balasubramanian, S.
AU - Baller, B.
AU - Barr, G.
AU - Barrow, J.
AU - Basque, V.
AU - Bathe-Peters, L.
AU - Benevides Rodrigues, O.
AU - Berkman, S.
AU - Bhanderi, A.
AU - Bhat, A.
AU - Bishai, M.
AU - Blake, A.
AU - Bolton, T.
AU - Book, J. Y.
AU - Camilleri, L.
AU - Caratelli, D.
AU - Caro Terrazas, I.
AU - Cavanna, F.
AU - Cerati, G.
AU - Church, E.
AU - Cianci, D.
AU - Conrad, J. M.
AU - Convery, M.
AU - Cooper-Troendle, L.
AU - Crespo-Anadón, J. I.
AU - Del Tutto, M.
AU - Dennis, S. R.
AU - Detje, P.
AU - Devitt, A.
AU - Diurba, R.
AU - Dorrill, R.
AU - Duffy, K.
AU - Dytman, S.
AU - Eberly, B.
AU - Ereditato, A.
AU - Fine, R.
AU - Fiorentini Aguirre, G. A.
AU - Fitzpatrick, R. S.
AU - Fleming, B. T.
AU - Foppiani, N.
AU - Franco, D.
AU - Nowak, J.
AU - Patel, N.
AU - Thorpe, C.
PY - 2022/9/12
Y1 - 2022/9/12
N2 - In this article, we describe a modified implementation of Mask Region-based Convolutional Neural Networks (Mask-RCNN) for cosmic ray muon clustering in a liquid argon TPC and applied to MicroBooNE neutrino data. Our implementation of this network, called sMask-RCNN, uses sparse submanifold convolutions to increase processing speed on sparse datasets, and is compared to the original dense version in several metrics. The networks are trained to use wire readout images from the MicroBooNE liquid argon time projection chamber as input and produce individually labeled particle interactions within the image. These outputs are identified as either cosmic ray muon or electron neutrino interactions. We find that sMask-RCNN has an average pixel clustering efficiency of 85.9% compared to the dense network's average pixel clustering efficiency of 89.1%. We demonstrate the ability of sMask-RCNN used in conjunction with MicroBooNE's state-of-the-art Wire-Cell cosmic tagger to veto events containing only cosmic ray muons. The addition of sMask-RCNN to the Wire-Cell cosmic tagger removes 70% of the remaining cosmic ray muon background events at the same electron neutrino event signal efficiency. This event veto can provide 99.7% rejection of cosmic ray-only background events while maintaining an electron neutrino event-level signal efficiency of 80.1%. In addition to cosmic ray muon identification, sMask-RCNN could be used to extract features and identify different particle interaction types in other 3D-tracking detectors.
AB - In this article, we describe a modified implementation of Mask Region-based Convolutional Neural Networks (Mask-RCNN) for cosmic ray muon clustering in a liquid argon TPC and applied to MicroBooNE neutrino data. Our implementation of this network, called sMask-RCNN, uses sparse submanifold convolutions to increase processing speed on sparse datasets, and is compared to the original dense version in several metrics. The networks are trained to use wire readout images from the MicroBooNE liquid argon time projection chamber as input and produce individually labeled particle interactions within the image. These outputs are identified as either cosmic ray muon or electron neutrino interactions. We find that sMask-RCNN has an average pixel clustering efficiency of 85.9% compared to the dense network's average pixel clustering efficiency of 89.1%. We demonstrate the ability of sMask-RCNN used in conjunction with MicroBooNE's state-of-the-art Wire-Cell cosmic tagger to veto events containing only cosmic ray muons. The addition of sMask-RCNN to the Wire-Cell cosmic tagger removes 70% of the remaining cosmic ray muon background events at the same electron neutrino event signal efficiency. This event veto can provide 99.7% rejection of cosmic ray-only background events while maintaining an electron neutrino event-level signal efficiency of 80.1%. In addition to cosmic ray muon identification, sMask-RCNN could be used to extract features and identify different particle interaction types in other 3D-tracking detectors.
KW - Particle identification methods
KW - Pattern recognition, cluster finding, calibration and fitting methods
KW - Time projection chambers
U2 - 10.1088/1748-0221/17/09/P09015
DO - 10.1088/1748-0221/17/09/P09015
M3 - Journal article
AN - SCOPUS:85144370972
VL - 17
JO - Journal of Instrumentation
JF - Journal of Instrumentation
SN - 1748-0221
IS - 9
M1 - P09015
ER -